[PATCH 19/21] drm/imagination: Add device_memory_force_cpu_cached override
Matt Coster
matt.coster at imgtec.com
Tue Nov 5 07:58:25 PST 2024
The TI k3-j721s2 platform has a bug relating to cache snooping on the AXI
ACE-Lite interface. Disabling cache snooping altogether would also resolve
the issue, but is considered more of a performance hit.
Given the platform is dma-coherent, forcing all device-accessible memory
allocations through the CPU cache is the preferred solution.
Implement this workaround so that it can later be enabled for the TI
k3-j721s2 platform.
Signed-off-by: Matt Coster <matt.coster at imgtec.com>
---
drivers/gpu/drm/imagination/pvr_device.c | 11 ++++++++++-
drivers/gpu/drm/imagination/pvr_device.h | 11 +++++++++++
drivers/gpu/drm/imagination/pvr_drv.c | 2 +-
drivers/gpu/drm/imagination/pvr_gem.c | 3 +++
drivers/gpu/drm/imagination/pvr_gem.h | 7 +++++--
drivers/gpu/drm/imagination/pvr_mmu.c | 7 ++++++-
6 files changed, 36 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/imagination/pvr_device.c b/drivers/gpu/drm/imagination/pvr_device.c
index 2ce46b9a8ab7609faebeeb4e7820751b00047806..ffc177c383c1be16061eff0290c347918b0991f7 100644
--- a/drivers/gpu/drm/imagination/pvr_device.c
+++ b/drivers/gpu/drm/imagination/pvr_device.c
@@ -24,6 +24,7 @@
#include <linux/gfp.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
+#include <linux/property.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/stddef.h>
@@ -635,6 +636,7 @@ bool
pvr_device_overrides_validate(struct pvr_device *pvr_dev,
const struct pvr_device_overrides *overrides)
{
+ struct drm_device *drm_dev = from_pvr_device(pvr_dev);
bool ret = true;
/*
@@ -643,7 +645,14 @@ pvr_device_overrides_validate(struct pvr_device *pvr_dev,
*
* Note that this function may be called early during device initialization
* so it should not be assumed that @pvr_dev is ready for normal use yet.
- */
+ */
+
+ if (overrides->device_memory_force_cpu_cached &&
+ device_get_dma_attr(drm_dev->dev) != DEV_DMA_COHERENT) {
+ drm_err(drm_dev,
+ "Specifying device_memory_force_cpu_cached override without dma-coherent attribute is unsupported.");
+ ret = false;
+ }
return ret;
}
diff --git a/drivers/gpu/drm/imagination/pvr_device.h b/drivers/gpu/drm/imagination/pvr_device.h
index ad0a02a37154099542247dfc62f411c10f4e41f4..7ae14899db24f4c747e8cf4d61d252eb403713f4 100644
--- a/drivers/gpu/drm/imagination/pvr_device.h
+++ b/drivers/gpu/drm/imagination/pvr_device.h
@@ -60,8 +60,19 @@ struct pvr_fw_version {
/**
* struct pvr_device_overrides - Hardware-level overrides loaded from
* MODULE_DEVICE_TABLE() or similar.
+ *
+ * @device_memory_force_cpu_cached: By default, all device memory buffer objects
+ * are mapped write-combined on the CPU (see %PVR_BO_CPU_CACHED) including MMU
+ * page table backing pages which do not use the regular device memory objects.
+ * This override forces all CPU mappings to be mapped cached instead. Since this
+ * could require additional cache maintenance operations to be performed,
+ * pvr_device_overrides_validate() ensures that the dma-coherent attribute is
+ * set when this override is specified. Required on some TI platforms where a
+ * bug causes device-to-cpu cache snooping to behave incorrectly when
+ * interacting with cpu-uncached memory.
*/
struct pvr_device_overrides {
+ bool device_memory_force_cpu_cached;
};
/**
diff --git a/drivers/gpu/drm/imagination/pvr_drv.c b/drivers/gpu/drm/imagination/pvr_drv.c
index b56ee2cda9b54c4388a6eef38b0ff81acdb05874..e074cfb0d2055b5387dbb142ca972108977f9854 100644
--- a/drivers/gpu/drm/imagination/pvr_drv.c
+++ b/drivers/gpu/drm/imagination/pvr_drv.c
@@ -1490,7 +1490,7 @@ static void pvr_remove(struct platform_device *plat_dev)
pvr_power_domains_fini(pvr_dev);
}
-static const struct pvr_device_overrides pvr_device_overrides_default = {};
+static const struct pvr_device_overrides pvr_device_overrides_default = { 0 };
/*
* Always specify &pvr_device_overrides_default instead of %NULL for &struct of_device_id->data so
diff --git a/drivers/gpu/drm/imagination/pvr_gem.c b/drivers/gpu/drm/imagination/pvr_gem.c
index 6a8c81fe8c1e85c2130a4fe90fce35b6a2be35aa..c67c30518f89af3de2e617a9b65e5cd78870fa2c 100644
--- a/drivers/gpu/drm/imagination/pvr_gem.c
+++ b/drivers/gpu/drm/imagination/pvr_gem.c
@@ -345,6 +345,9 @@ pvr_gem_object_create(struct pvr_device *pvr_dev, size_t size, u64 flags)
if (size == 0 || !pvr_gem_object_flags_validate(flags))
return ERR_PTR(-EINVAL);
+ if (PVR_HAS_OVERRIDE(pvr_dev, device_memory_force_cpu_cached))
+ flags |= PVR_BO_CPU_CACHED;
+
shmem_obj = drm_gem_shmem_create(from_pvr_device(pvr_dev), size);
if (IS_ERR(shmem_obj))
return ERR_CAST(shmem_obj);
diff --git a/drivers/gpu/drm/imagination/pvr_gem.h b/drivers/gpu/drm/imagination/pvr_gem.h
index e0e5ea509a2e88a437b8d241ea13c7bab2220f56..9b3cbcbe48dfbbc8be211a8a409699a43452e178 100644
--- a/drivers/gpu/drm/imagination/pvr_gem.h
+++ b/drivers/gpu/drm/imagination/pvr_gem.h
@@ -44,8 +44,11 @@ struct pvr_file;
* Bits not defined anywhere are "undefined".
*
* CPU mapping options
- * :PVR_BO_CPU_CACHED: By default, all GEM objects are mapped write-combined on the CPU. Set this
- * flag to override this behaviour and map the object cached.
+ * :PVR_BO_CPU_CACHED: By default, all GEM objects are mapped write-combined on the CPU. Set
+ * this flag to override this behaviour and map the object cached. If
+ * &struct pvr_device_overrides->device_memory_force_cpu_cached is specified, all allocations
+ * will be mapped as if this flag was set. This does not require any additional consideration
+ * at allocation time since the override is only valid if the dma-coherent attribute is set.
*
* Firmware options
* :PVR_BO_FW_NO_CLEAR_ON_RESET: By default, all FW objects are cleared and reinitialised on hard
diff --git a/drivers/gpu/drm/imagination/pvr_mmu.c b/drivers/gpu/drm/imagination/pvr_mmu.c
index 4fe70610ed94cf707e631f8148af081a94f97327..7c7deb29b735308eaed26900f2f54a838382c255 100644
--- a/drivers/gpu/drm/imagination/pvr_mmu.c
+++ b/drivers/gpu/drm/imagination/pvr_mmu.c
@@ -259,6 +259,7 @@ pvr_mmu_backing_page_init(struct pvr_mmu_backing_page *page,
struct device *dev = from_pvr_device(pvr_dev)->dev;
struct page *raw_page;
+ pgprot_t prot;
int err;
dma_addr_t dma_addr;
@@ -268,7 +269,11 @@ pvr_mmu_backing_page_init(struct pvr_mmu_backing_page *page,
if (!raw_page)
return -ENOMEM;
- host_ptr = vmap(&raw_page, 1, VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+ prot = PAGE_KERNEL;
+ if (!PVR_HAS_OVERRIDE(pvr_dev, device_memory_force_cpu_cached))
+ prot = pgprot_writecombine(prot);
+
+ host_ptr = vmap(&raw_page, 1, VM_MAP, prot);
if (!host_ptr) {
err = -ENOMEM;
goto err_free_page;
--
2.47.0
More information about the linux-arm-kernel
mailing list